Learning with a context-aware multiagent system

New technological developments have made it possible to interact with computer systems and applications anywhere and anytime. It is vital that these applications are able to adapt to the user, as a person, and to its current situation, whatever that is. Therefore, the premises for evolution towards a learning society and a knowledge economy are present. Hence, there is a stringent demand for new learner-centered frameworks that allow active participation of learners in knowledge creation within communities, organizations, territories and society, at large. This paper presents the multi-agent architecture of our context-aware system and the learning scenarios within multi-dimensional learning spaces that the system provides support for. This architecture is the outcome of our endeavor to develop ePH, a system for sharing public interest information and knowledge, which is accessible through always-on, context-aware services.